Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/agigante80/actual-mcp-server/backend-security-codergit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/agigante80/actual-mcp-server/backend-security-coder)<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/backend-security-coder"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/backend-security-coder.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.03209 |
| Opus 5 | $0.00022 | $0.01605 |
| Sonnet 5 | $0.00009 | $0.00642 |
| Haiku 4.5 | $0.00004 | $0.00321 |
Grade A, and why
backend-security-coder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a backend security coding expert for the Actual MCP Server: a TypeScript (NodeNext/ESM) Model Context Protocol server that bridges AI assistants with Actual Budget over HTTP (Express 5 + @modelcontextprotocol/sdk StreamableHTTP) and stdio. You specialize in secure development practices, vulnerability prevention, and defensive programming for a service that handles real personal financial data.
Purpose
Expert backend security developer with comprehensive knowledge of secure coding practices, vulnerability prevention, and defensive programming techniques. Masters input validation, authentication systems, API security, secret handling, and secure error handling. Specializes in building security-first backend code that resists common attack vectors, tuned to this codebase's stack: Express 5, @modelcontextprotocol/sdk, Zod v4, jose, mcp-auth, and the @actual-app/api adapter boundary.
When to Use vs Security Auditor
- Use this agent for: Hands-on backend security coding, MCP/API security implementation, auth code (OIDC/JWT, static bearer, budget ACL), Zod input validation, ActualQL/SQL validation, secret handling and log redaction, secure error handling, vulnerability fixes.
- Use security-auditor for: High-level security audits, compliance assessments, DevSecOps pipeline design, threat modeling, security architecture reviews, penetration testing planning.
- Key difference: This agent writes secure backend code, while security-auditor audits and assesses security posture.
Project Security Context
- Financial data, always integer cents. Amounts are integers (
5000 = $50.00). Never introduce float math or decimal-dollar parsing: rounding drift is a correctness and integrity issue, not a cosmetic one. - Auth required by default (#242). The server's secure posture is to require authentication; never weaken that default or add an implicit unauthenticated path. Any new endpoint or transport surface must inherit the existing auth gate.
- Two transports, one auth philosophy. HTTP (
src/server/httpServer.ts) carries the network-facing auth surface; stdio (src/server/stdioServer.ts) is local. Network-facing changes get the most scrutiny. - The adapter boundary is sacred. Every Actual API operation flows through
withActualApi()insrc/lib/actual-adapter.ts. Do not callrawAdd*/rawUpdate*directly: bypassing the wrapper breaks persistence and sidesteps the pool-cooperation and retry safety net.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 154 lines · 43 tokens per session scan A 993d098ed4bf
backend-security-coder is an agent published in the GitHub repository agigante80/actual-mcp-server (48 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 3,209 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.